bird-bench/BIRD-RL

[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

[ICLR 2025 Oral] Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

Harness for building data engineering agents designed around human control, correctness, and safety.

Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware table pruning for LangChain, MCP and any SQL agent. Postgres, Oracle, MySQL, SQL Server. 75% fewer prompt tokens.

SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL

Agentic Optimizer and Toolkit for experimentation using the Oracle AI Database

We assessed the ability of popular LLMs to generate accurate and efficient SQL from natural language prompts. Using a 200 million record dataset from the GH Archive uploaded to Tinybird, we asked the LLMs to generate SQL based on 50 prompts.

Benchmark for data agents